How to Use the Comet ML MCP in Cursor

Q: How does Cursor use Comet ML parameters to write code?

Cursor executes getexperimentparams to read your API taxonomy types. It then generates python scripts that match your exact log structure.

Q: How do I configure this Comet ML MCP Server in Cursor?

Add the server details to your .cursor/mcp.json file. Once saved, Cursor detects the tools and lets you query your experiments.

Q: Does Cursor let me search my logged experiments?

Yes, Cursor runs listexperiments to extract the routing arrays. You get a list of active runs without leaving your code file.

Write training scripts in Cursor using live Comet ML experiment metrics and parameter values.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comet ML MCP to Cursor

Create your Vinkius account to connect Comet ML to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Comet ML with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Comet ML workspaces directly in Cursor

The `list_workspaces` tool identifies your headless routing spaces to let Cursor know where your models live. This MCP Server lets your agent write code tailored to your exact workspace setup. Running `list_projects` pulls the underlying project structures into your editor. Cursor reads these structures to generate accurate API calls that target the correct project paths.

Generate code using live run parameters

The `get_experiment_params` tool pulls exact taxonomy properties directly into Cursor's active context window. You can write evaluation scripts based on actual run configurations instead of guessing variable names. If you need to trace a specific run, Cursor uses `get_experiment` to look up payload IDs. This lets you debug failing pipelines by comparing your local code against the logged cloud tracing data.

Debug model metrics using this MCP Server

The `get_experiment_metrics` tool retrieves defined numeric bounds directly inside your Cursor workspace. Your agent analyzes these training curves to suggest code changes for your hyperparameters. You can run `list_experiments` to check limits across multiple logged runs. Cursor parses these arrays to help you write script updates that target your best-performing models.

Setup guide

Set up Comet ML MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Comet ML MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Comet ML transactions." If the MCP tools are loaded correctly, Cursor will call the Comet ML tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "comet-ml-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Comet ML. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Comet ML now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Comet ML MCP in Cursor

Cursor executes `get_experiment_params` to read your API taxonomy types. It then generates python scripts that match your exact log structure.

Yes, you can ask Cursor's agent to check your training runs. It calls `get_experiment_metrics` to grab your numeric bounds and displays them in your editor sidebar.

Add the server details to your `.cursor/mcp.json` file. Once saved, Cursor detects the tools and lets you query your experiments.

Yes, Cursor runs `list_experiments` to extract the routing arrays. You get a list of active runs without leaving your code file.

This MCP server processes your numerical metrics, project names, and workspace details locally through Cursor's isolated process manager. Your raw ML run parameters and training metrics are never stored on external staging servers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript